jd-opensource / jd-opensource/JoyAI-VL-Interaction
使用摄像头的RTSP拉流传输视频，限制了16K的上下文（只占用A6000单卡30多G显存），持续监控几分钟后显存占用超出大小
Open
- Dominant language
- Python
- Stars
- 1.9k
- Forks
- 190
- PR merge metrics
- No merged PRs in 30d
Description
有办法解决RTSP一直拉流，会堆积占满显存的问题吗，我试了面壁智能的那个模型好像也会有这个问题
Contributor guide
No contributing guide indexed for this repository
Research direction
Reproduce the RTSP stream with the reported 16K context on an A6000 and monitor GPU memory for several minutes. The issue names no files or tests, so first locate the RTSP ingestion and video/context buffering entry points. Done means sustained streaming no longer accumulates frames or exceeds available GPU memory.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, audio-video-rtc
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100